English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We address the challenge of applying existing convolutional neural network(CNN) architectures to compressed images. Existing CNN architectures representimages as a matrix of pixel intensities with a specified dimension; thisdesired dimension is achieved by downgrading or cropping. Downgrading andcropping are attractive in that the result is also an image; however, analgorithm producing an alternative "compressed" representation could yieldbetter classification performance. This compression algorithm need not bereversible, but must be compatible with the CNN's operations. This problem isthus the counterpart of the well-studied problem of applying compressed CNNs touncompressed images, which has attracted great interest as CNNs are deployed tosize-, weight-, and power- (SWaP)-limited devices. We introduce LocalizedCompression, a generalization of downgrading in which the original image isdivided into blocks and each block is compressed to a smaller size using eithersampling- or random-matrix-based techniques. By aligning the size of thecompressed blocks with the size of the CNN's convolutional region, localizedcompression can be made compatible with any CNN architecture. Our experimentalresults show that Localized Compression results in classification accuracyapproximately 1-2% higher than is achieved by downgrading to the equivalentresolution.

Localized Compression: Applying Convolutional Neural Networks to Compressed Images